Rank resumes by job description similarity using OpenRouter embeddings

Quick overview

This workflow collects resume PDFs and a job description through an n8n form, extracts text (with OCR for scanned PDFs), generates embeddings via OpenRouter, and ranks the resumes by cosine similarity to the job description, returning a CSV-style list of ranked filenames.

How it works

1. Receives resume PDFs and a job description from an n8n form submission.
2. Creates an embedding for the job description using OpenRouter’s embeddings endpoint with openai/text-embedding-3-large.
3. Processes each uploaded resume one at a time, converting the PDF to text using built-in PDF extraction.
4. If the extracted text is too short (likely scanned), sends the PDF to OpenRouter chat completions with the file-parser plugin (mistral-ocr) to OCR the document and return plain text.
5. Creates an embedding for each resume’s extracted text (from direct extraction or OCR) using openai/text-embedding-3-large.
6. Computes cosine similarity between each resume embedding and the job description embedding, then sorts resumes from most similar to least similar.
7. Returns a completion page containing a CSV-style list of rank and filename.

Setup

1. Add an OpenRouter API credential in n8n and select it on the embedding and OCR HTTP request steps.
2. Ensure your OpenRouter account has access to openai/text-embedding-3-large, google/gemma-4-31b-it, and the file-parser plugin with mistral-ocr for scanned PDF extraction.
3. Open the workflow’s form trigger in a browser, upload one or more PDF resumes, and paste the job description before running.